mlsanityData to 14 Oct 2026

Meta-reinforcement learning with minimum attention

arXiv 2505.16741 ↗First posted 22 May 2025cs.LG math.OC stat.MLcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Minimum attention applies the least action principle in changes of control concerning state and time, first proposed by Brockett. The involved regularization is highly relevant in emulating biological control, such as motor learning. We apply minimum attention in reinforcement learning (RL) as part of the rewards and investigate its connection to meta-learning and stabilization. Specifically, model-based meta-learning with minimum attention is explored in high-dimensional nonlinear dynamics. Ensemble-based model learning and gradient-based meta-policy learning are alternately performed. Empirically, minimum attention improves fast adaptation in few shots and reduces variance from perturbations of the model and environment, compared to model-free and model-based RL baseline, and yields consistent gain when integrated into modern world models (DreamerV3, MAMBA). Furthermore, the minimum attention demonstrates an improvement in energy efficiency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 21 of its 29 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

21 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning14 Mar

Other references · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2015Trust Region Policy Optimizationcited by 2,580
  5. 2023Mastering Diverse Domains through World Modelscited by 1,253
  6. 2018DeepMind Control Suitecited by 956
  7. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  8. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 219
  9. 2019Robust Learning with Jacobian Regularizationcited by 129
  10. 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 101
  11. 2020Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learningcited by 98
  12. 2021Differentiable Particle Filtering via Entropy-Regularized Optimal Transportcited by 59
8 more
  1. 2020The Advantage of Conditional Meta-Learning for Biased Regularization and Fine-Tuningcited by 40
  2. 2021Policy Smoothing for Provably Robust Reinforcement Learningcited by 40
  3. 2020Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEscited by 32
  4. 2022Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regimecited by 21
  5. 2023Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Functioncited by 19
  6. 2020Online Meta-Critic Learning for Off-Policy Actor-Critic Methodscited by 17
  7. 2022Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularizationcited by 8
  8. 2019On the Existence and Computation of Minimum Attention Optimal Control Lawscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
  2. 2024Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery
  3. 2024Towards an Adaptable and Generalizable Optimization Engine in Decision and Control: A Meta Reinforcement Learning Approach
  4. 2023Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation
  5. 2023Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes
  6. 2024Constrained Meta Agnostic Reinforcement Learning
  7. 2022Robotic Control Using Model Based Meta Adaption
  8. 2024Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees